net.load_state_dict(state_dict, assign=True) 失败

非常感谢你的开源工作。按照你推荐的环境，我已经跑通了你默认的I2V脚本：
python turbodiffusion/inference/wan2.2_i2v_infer.py
--model Wan2.2-A14B
--low_noise_model_path checkpoints/TurboWan2.2-I2V-A14B-low-720P-quant.pth
--high_noise_model_path checkpoints/TurboWan2.2-I2V-A14B-high-720P-quant.pth
--resolution 720p
--adaptive_resolution
--image_path assets/i2v_inputs/i2v_input_0.jpg
--prompt "POV selfie video, ultra-messy and extremely fast. A white cat in sunglasses stands on a surfboard with a neutral look when the board suddenly whips sideways, throwing cat and camera into the water; the frame dives sharply downward, swallowed by violent bursts of bubbles, spinning turbulence, and smeared water streaks as the camera sinks. Shadows thicken, pressure ripples distort the edges, and loose bubbles rush upward past the lens, showing the camera is still sinking. Then the cat kicks upward with explosive speed, dragging the view through churning bubbles and rapidly brightening water as sunlight floods back in; the camera races upward, water streaming off the lens, and finally breaks the surface in a sudden blast of light and spray, snapping back into a crooked, frantic selfie as the cat resurfaces."
--num_samples 1
--num_steps 4
--quant_linear
--attention_type sagesla
--sla_topk 0.1
--ode
但是当我仅把--attention_type的值设置为original的时候会出现Unexpected key(s) in state_dict: "blocks.0._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.weight", "blocks.0._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.bias", "blocks.1._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.weight", "blocks.1._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.bias", "blocks.2._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.weight", "blocks.2._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.bias", "blocks.3._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.weight", "blocks.3._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.bias", "blocks.4._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.weight", "blocks.4._checkpoint_wrapped_module.self_attn.attn_op.local_attn.proj_l.bias", "blocks.5._checkpoint....之类的错误

请问该如何有效解决呢 十分期待你的回复~谢谢

Start with turbodiffusion/inference/wan2.2_i2v_infer.py and trace model loading when --attention_type original is selected. Compare the checkpoint keys containing local_attn.proj_l with the model's expected keys; done means the default I2V command runs with original attention without Unexpected key(s) errors.